© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 39254
    Prev
    Next
    INDEX
    Explanations

    son, ect, semble, strobe, Glove, SAFE, amble, locale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resiliency
    0.64
    quinazolin
    0.62
    䬲
    0.58
    pyridazin
    0.54
    quinolin
    0.54
    pyrimidin
    0.54
     Chromium
    0.54
    郏
    0.51
    panelMenuList
    0.50
     Державний
    0.50
    POSITIVE LOGITS
    raine
    1.00
    lande
    0.97
     Christine
    0.95
    liste
    0.94
     Simone
    0.93
    garde
    0.91
     Maxime
    0.91
    туре
    0.91
    texte
    0.90
    kube
    0.89
    Activations Density 0.334%

    No Known Activations